CN116579576A - Intelligent decision aquaculture tracing method and system based on blockchain - Google Patents
Intelligent decision aquaculture tracing method and system based on blockchain Download PDFInfo
- Publication number
- CN116579576A CN116579576A CN202310595213.2A CN202310595213A CN116579576A CN 116579576 A CN116579576 A CN 116579576A CN 202310595213 A CN202310595213 A CN 202310595213A CN 116579576 A CN116579576 A CN 116579576A
- Authority
- CN
- China
- Prior art keywords
- data
- aquaculture
- production
- blockchain
- intelligent decision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009360 aquaculture Methods 0.000 title claims abstract description 144
- 244000144974 aquaculture Species 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims abstract description 98
- 238000012544 monitoring process Methods 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 8
- 238000004806 packaging method and process Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 5
- 239000000969 carrier Substances 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000005538 encapsulation Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 14
- 239000013598 vector Substances 0.000 description 12
- 238000001514 detection method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 239000001301 oxygen Substances 0.000 description 5
- 229910052760 oxygen Inorganic materials 0.000 description 5
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000009395 breeding Methods 0.000 description 3
- 230000001488 breeding effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 238000006213 oxygenation reaction Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000005276 aerator Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000003306 harvesting Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- QVYRGXJJSLMXQH-UHFFFAOYSA-N orphenadrine Chemical compound C=1C=CC=C(C)C=1C(OCCN(C)C)C1=CC=CC=C1 QVYRGXJJSLMXQH-UHFFFAOYSA-N 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000003169 complementation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/05—Underwater scenes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Agronomy & Crop Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Mining & Mineral Resources (AREA)
- Medical Informatics (AREA)
- Marine Sciences & Fisheries (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Animal Husbandry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an intelligent decision aquaculture tracing method and system based on a blockchain, wherein the method comprises the following steps: constructing an aquaculture traceability alliance blockchain according to the production flow of the aquatic products; monitoring each production link of the aquatic product to obtain production link data and environment multi-source data, and uploading the production link data and the environment multi-source data to a alliance block chain; collecting mass aquaculture data and constructing an aquaculture knowledge base; performing parameter optimization on the decision model according to the constructed aquaculture knowledge base to obtain an aquaculture intelligent decision model; and inputting the real-time environment multi-source data into an aquaculture intelligent decision model to obtain a production decision and uploading the production decision to the alliance blockchain. The system comprises: the system comprises an aquatic product data whole-flow acquisition module, a production intelligent decision module and a alliance block chain network module. The application can reduce the intervention of manpower on the tracing chain and improve the reliability of tracing the aquatic products. The application can be widely applied to the technical field of block chain application.
Description
Technical Field
The application relates to the technical field of blockchain application, in particular to an intelligent decision aquaculture tracing method and system based on blockchains.
Background
In recent years, food safety events are layered endlessly worldwide, the safety risk of aquatic products is increased day by day, and consumers pay high attention to the safety problem of the aquatic products. In order to ensure food safety, various product traceability systems are applied to food retail links so as to relieve anxiety of consumers on food safety and improve the problem of difficult food safety supervision.
In the traditional aquaculture, the bottleneck problems that the data of the whole industrial chain of the aquaculture are inaccurate, the aquaculture disasters are outstanding, the aquaculture production is accurate, the aquatic products cannot be traced, the food safety cannot be guaranteed and the like exist. The culture data is usually stored centrally, the authenticity of the data is difficult to ensure, and the risk of tampering with the data due to the benefit of the culture data exists. In addition, in the links of fry breeding, growth, processing and the like, each enterprise on a supply chain keeps accounts to form an information island, so that data is difficult to trace. Moreover, because the information resources are scattered and independent, the information resources are difficult to share and update in time, so that the information practicability and timeliness are poor. Therefore, the existing aquatic product traceability system still needs a large amount of manual operations to record data, and is difficult to ensure the operation specification of data record personnel, and the reliability of the traceability information of the existing aquatic product traceability system still needs to be further enhanced although the non-tamperable characteristic of the blockchain technology is utilized.
Disclosure of Invention
In order to solve the technical problems, the application aims to provide the intelligent decision aquaculture tracing method and system based on the blockchain, which designs automatic acquisition and periodic automatic chaining of growth environment multi-source data and production link data in the aquaculture production process, adopts an intelligent decision technology to analyze and decide according to actual aquaculture conditions and chaining decision information, reduces manual intervention on the tracing chain, and improves the reliability of aquatic product tracing.
The first technical scheme adopted by the application is as follows: an intelligent decision aquaculture tracing method based on block chain comprises the following steps:
constructing an aquaculture traceability alliance blockchain according to the production flow of the aquatic products;
monitoring each production link of the aquatic product to obtain production link data and storing the production link data into a alliance block chain;
monitoring the aquatic product growth environment to obtain environment multi-source data and periodically uploading the environment multi-source data to a alliance blockchain;
constructing an intelligent decision model according to the aquaculture knowledge base and performing parameter optimization to obtain the aquaculture intelligent decision model;
and inputting the real-time environment multi-source data into an aquaculture intelligent decision model to obtain a production decision and uploading the production decision to the alliance blockchain.
Further, the blockchain-based intelligent decision aquaculture tracing method further comprises the steps of collecting aquaculture data and constructing an aquaculture knowledge base, and specifically comprises the following steps:
dividing an initial aquaculture knowledge base to obtain a classification knowledge base;
acquiring aquaculture data and classifying to obtain classified data;
updating the classification knowledge base based on the classification data to obtain a final aquaculture knowledge base.
By this preferred step, an aquaculture database can be constructed that can update knowledge of the data in real time, and the large amount of data stored in this database can support the subsequent intelligent decision-making to improve the data aspect.
Further, the step of constructing the aquaculture traceability alliance blockchain according to the production flow of the aquatic products specifically comprises the following steps:
dividing and deploying alliance blockchain members according to the aquatic product production flow to obtain an alliance blockchain network;
coding according to a preset standard coding format based on each circulation link of the aquatic product to obtain a alliance block chain traceability code;
and formulating relevant configuration files based on a consistent scheme of alliance members, and combining an alliance blockchain network and alliance blockchain traceability codes to obtain the aquaculture traceable alliance blockchain.
Through the preferred steps, the coding format of the aquaculture traceable alliance blockchain is determined, and an alliance blockchain network represented by fishermen, processors, logistics providers and sellers is formed.
Further, the step of monitoring the production link of the aquatic product to obtain production link data and storing the production link data in the alliance blockchain specifically comprises the following steps:
dividing the production links of the aquatic products into stages to obtain a seedling raising stage, a feeding and growing stage, a processing and packaging stage, a logistics stage and a sales stage;
monitoring each production link of the aquatic product to obtain production link data;
and storing the data of each production link into an independent blockchain network through a multi-chain data storage mode, and generating the traceability information of each link.
Through the optimization step, automatic acquisition and periodic automatic uplink of production link data in the aquaculture process are completed, and the credibility of the data can be improved through a single blockchain storage network.
Further, the step of monitoring the aquatic product growth environment to obtain environment multisource data and periodically uploading the environment multisource data to a alliance blockchain, wherein the monitoring mode of the aquatic product growth environment is 'space-earth' integrated high-precision multidimensional three-dimensional monitoring, and 'space-earth' integrated is that comprehensive acquisition of aquatic product data is performed by comprehensively using space-based equipment, space-based equipment and foundation equipment, wherein:
the space-based equipment comprises a high-resolution satellite and a multi-source satellite; the space-based equipment comprises unmanned aerial vehicle aerial survey and airborne laser radar; the foundation equipment comprises a fixed sensor and portable acquisition equipment; the multi-source data of the growth environment are multi-source heterogeneous data of the growth environment of the aquatic product, which are acquired by using various acquisition equipment; the acquisition equipment comprises a high-resolution remote sensing satellite, an unmanned aerial vehicle, a ground sensor and a multi-angle camera, so as to acquire data such as gas, temperature and humidity, soil, illumination, weather, water quality and the like.
Through the optimization step, the detection uploading of the aquatic product growth environment can be avoided from being manually interfered, and the credibility of the environment multi-source data is improved.
Further, the step of constructing an intelligent decision model according to the aquaculture knowledge base and performing parameter optimization to obtain the aquaculture intelligent decision model specifically comprises the following steps:
dividing the association relation between the growth environment multisource data and the decision result in the aquaculture knowledge base to obtain knowledge nodes and inference nodes;
constructing an intelligent decision model based on knowledge nodes and initializing to obtain initialization parameters;
performing attribute similarity matching on the inferred node and the knowledge node to obtain correct mapping from the inferred node to the knowledge node;
and optimizing parameters of the intelligent decision model based on the correct mapping to obtain the aquaculture intelligent decision model.
Through the optimization step, parameter optimization of the decision model is completed, and accurate decision judgment can be better made based on real-time environment multi-source data.
The second technical scheme adopted by the application is as follows: an intelligent decision-making aquaculture traceability system based on a blockchain, comprising:
the aquatic product data whole-flow acquisition module is used for acquiring multi-source data of a growth environment and production link data;
the production intelligent decision-making module is used for carrying out decision-making inference by combining the knowledge graph according to the aquatic product knowledge and the growth environment multisource data and the production link data provided by the aquatic product data whole-flow acquisition module so as to obtain a production decision;
the alliance blockchain network module is used for tracing the aquaculture production process through cloud service and blockchain technology;
the aquatic product data whole-flow collection module is connected with the alliance blockchain network module and is used for uploading the collected growth environment multi-source data and the production link data to the alliance blockchain network module;
the aquatic product data whole-flow acquisition module is connected with the production intelligent decision module and is used for providing acquired growth environment multi-source data and production link data;
the production intelligent decision module is connected with the alliance block chain network module and is used for uploading production decisions to the alliance block chain network module.
Further, the production intelligent decision module comprises an aquatic knowledge base unit and an intelligent decision unit, wherein:
the aquatic product knowledge base unit is used for carrying out big data analysis and processing on aquatic product scene data and knowledge extraction and fusion to obtain knowledge of aquatic product tissues after encapsulation;
the intelligent decision unit is used for carrying out decision inference according to the comprehensive data provided by the aquatic product knowledge base unit and the growth environment multi-source data provided by the aquatic product data whole-flow acquisition module to obtain decision information.
Further, the federated blockchain network module includes an object identification layer, a data acquisition layer, a data processing layer, and a data service layer, wherein:
the object identification layer is used for generating and managing traceability codes and coded data carriers of aquatic products and various circulation links thereof;
the data acquisition layer is used for reading and analyzing the coded data carrier and uploading the data to the back-end database according to the address information in the data unit;
the data processing layer is used for processing the acquired data and storing the acquired data into a block chain network;
the data service layer is used for processing a query request of a consumer end and checking whether the full-chain data is tampered or not to obtain full-chain traceability information of the corresponding aquatic products.
The method and the system have the beneficial effects that: according to the application, through designing the automatic acquisition and periodic automatic uplink of the growth environment multisource data and the production link data in the aquaculture production process, the manual intervention is reduced, and the credibility of the traceability data is improved; the intelligent aquaculture decision model is adopted to analyze and decide the environmental multisource data of the actual aquaculture condition and to link the decision information, so that manual intervention is further reduced, the intelligentization and the accuracy of the decision in the production process are realized, the credibility of the decision information is improved, and the establishment of the credibility traceability of distributed, non-tamperable and value transmissible aquaculture production process is realized.
Drawings
FIG. 1 is a flow chart of steps of a blockchain-based intelligent decision aquaculture traceability method of the present application;
FIG. 2 is a block diagram of a blockchain-based intelligent decision aquaculture traceability system;
fig. 3 is a schematic diagram of traceability information transmission of an aquatic product growth link according to an embodiment of the blockchain-based intelligent decision aquaculture traceability method.
Detailed Description
The application will now be described in further detail with reference to the drawings and to specific examples. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
Referring to fig. 1, the application provides a blockchain-based intelligent decision aquaculture traceability method, which comprises the following steps:
s1, constructing an aquaculture traceability alliance block chain according to an aquatic product production process;
s1.1, dividing and deploying alliance blockchain members according to an aquatic product production flow to obtain an alliance blockchain network;
specifically, the aquatic product production process can be divided into 4 basic processes of cultivation, management, consumption and management, and alliance blockchain members are divided into breeders, operators, consumers and managers according to the basic processes; dividing ports for each alliance blockchain member into a breeder port, an operator port, a consumer port and a manager port; namely, a fishing ground, a fishery user, an authentication mechanism, a food processing enterprise, a sales enterprise, a logistics storage enterprise and the like are distributed to corresponding alliance blockchain ports, and each port and alliance blockchain member to which the port belongs are mutually connected to form an alliance blockchain network.
S1.2, coding according to a preset standard coding format based on each circulation link of the aquatic product to obtain a alliance block chain traceability code;
specifically, the traceability codes are created according to an application identifier AI provided by the GS1 standard, and comprise aquatic product producer codes, production place codes, aquatic product project codes, product batch codes, different package form codes, other production raw material codes, aquatic product circulation codes and other allied blockchain traceability codes, and a consumer can scan the traceability codes through a mobile client to acquire traceability information in the traceability codes.
S1.3, formulating relevant configuration files based on a consistent scheme of alliance members, and combining an alliance blockchain network and alliance blockchain traceability codes to obtain the aquaculture traceable alliance blockchain.
Specifically, an account configuration file is formulated according to an agreed scheme of alliance members, and then an account and a secret key are generated for each organization and ordering nodes, peer nodes and the like in the organization according to the configuration file, and a CA service is started; making a sequencing service configuration file according to a scheme agreed by alliance members, generating a sequencing service creation block according to the configuration file, and starting the sequencing service; formulating a peer node configuration file according to a scheme agreed by alliance members, and starting the peer node according to the configuration file; establishing a channel configuration file according to a scheme agreed by alliance members, and generating a channel creation block according to the configuration file; according to an agreed upon scheme by the federation members, a request is joined to the channel with the certificate of the peer node. After the corresponding nodes are prepared, the alliance block chain network and the alliance block chain traceability codes are combined to jointly construct the aquaculture traceability alliance block chain.
S2, monitoring the aquatic product production links to obtain production link data and storing the production link data into a alliance block chain;
s2.1, carrying out stage division on the production links of the aquatic products to obtain a seedling raising stage, a feeding and growing stage, a processing and packaging stage, a logistics stage and a sales stage;
s2.2, carrying out all-round monitoring on all production links of the aquatic products to obtain production link data;
specifically, the monitoring data of the seedling stage comprises a fish fry source evidence and a detection analysis report; the feeding and growing stage data comprise environment accurate monitoring, seed selection quality recording, feed application recording and growth harvest recording, wherein the recording covers the whole period of the feeding and growing stage and is recorded once in units of days, and the environment accurate monitoring is 'space-ground' integrated high-precision multidimensional three-dimensional monitoring; the processing and packaging stage data mainly uses a multi-angle camera to shoot the real-time information of the environment and the operation of operators; the logistics stage data comprise accurate departure date, arrival date, a real-time transportation route map and real-time monitoring of temperature change in a transportation compartment through a camera; the sales phase data mainly includes selling price, quality of the sold product, out-of-stock rate and out-of-stock period.
S2.3, storing the data of each production link into an independent blockchain network through a multi-chain data storage mode, and generating the traceability information of each link.
Specifically, the data storage of the alliance blockchain adopts a multi-chain mode, and the data of different links is stored by using a single blockchain network. And deploying authentication nodes for each role node, when data is transmitted, initiating uplink transaction by the nodes, determining the node sequence of preferential processing through sequencing service, then determining the node for obtaining the accounting right through a consensus mechanism, recording the transaction, and simultaneously, automatically backing up account books by each node and retaining the lower trace information. As shown in fig. 3, except the original node, each link needs to inherit the tracing information of the previous link, generate the tracing information of the current link, and upload the tracing information of the current link to the blockchain after adding the relevant connection information, and meanwhile, the tracing information of the current link is transferred to the next link through the physical label for use by the subsequent links.
S3, monitoring the aquatic product growth environment to obtain environment multi-source data and periodically uploading the environment multi-source data to a alliance block chain;
the aquatic product growth environment is monitored in a 'space-sky-earth' integrated mode, and the aquaculture growth process is monitored in a high-precision multidimensional and three-dimensional mode, namely, space-based equipment and foundation equipment are comprehensively used for comprehensively acquiring aquatic product data; in particular, the space-based devices include high-resolution satellites, multi-source satellites; the space-based equipment comprises unmanned aerial vehicle aerial survey and airborne laser radar; the foundation equipment comprises a fixed sensor and portable acquisition equipment; the multi-source data of the growth environment are multi-source heterogeneous data of the growth environment of the aquatic product, which are acquired by using various acquisition equipment; the acquisition equipment comprises a high-resolution remote sensing satellite, an unmanned aerial vehicle, a ground sensor and a multi-angle camera. Through remote sensing network, thing networking and internet three-network integration technique, according to aquaculture local pond and specific shape, dispose high-resolution remote sensing satellite, unmanned aerial vehicle, ground sensor, multi-angle camera and carry out data acquisition, ground sensor includes water quality sensor, weather class sensor, utilizes above-mentioned equipment can acquire the real-time data of growing environment, including aquaculture pond change detection diagram, target water area's temperature, conductivity, PH, dissolved oxygen, ORP and ammonia nitrogen, and underwater image data.
Screening the original data of the aquatic product growth environment multisource data acquired in real time, selecting a valuable data part for aquaculture, further analyzing the screened multisource data so as to facilitate reading by a culture practitioner and a consumer, and storing the analyzed data into a rear-end database; the data of the rear database is not manually interfered, the processed aquatic product growth environment multisource data is periodically stored in the alliance block chain, and the aquatic product growth environment multisource data belongs to the data of the feeding growth stage in the production link.
S4, acquiring aquaculture data and constructing an aquaculture knowledge base;
s4.1, dividing an initial aquaculture knowledge base to obtain a classification knowledge base;
specifically, according to the data types required to be stored in the aquaculture knowledge base, the aquaculture knowledge base is subjected to database subdivision, and the aquaculture knowledge base comprises an aquaculture basic database, an aquaculture resource database, an aquaculture knowledge interaction information base and an aquaculture related case base. Wherein the aquaculture basic database comprises various aquaculture water quality information, various aquatic product variety information and basic common sense knowledge and concepts of some aquaculture; the data of the aquaculture resource database does not directly participate in decision making, but helps to focus and position problems so as to assist decision making, including water resource information, land resource information, climate resource information, forest resource information and aquaculture natural disaster information; the data of the aquaculture knowledge interaction information base is derived from working experience of aquaculture practitioners, and comprises aquaculture technology experience communication information, aquaculture technology interest communication information and aquaculture technology electronic prescriptions; the aquaculture related case library comprises aquaculture technical solutions and related success cases.
S4.2, acquiring aquaculture data and classifying to obtain classified data;
specifically, mass aquaculture data are collected from networks and documents through data mining technology. Information extraction and analysis are carried out on aquaculture data, occurrence relations and rules between the data are found, aquaculture product knowledge is organized, packaged and classified, the classification knowledge base is stored, and the use of the knowledge base is stored on a block chain; the step of extracting information comprises named entity identification, relation extraction and event extraction.
Named entity recognition employs a BiLSTM-CRF model that includes a presentation layer, a BiLSTM layer, and a CRF layer. The representation layer represents each sentence in massive aquaculture data as a word vector and a word vector, the BiLSTM layer outputs the input word vector and the word vector as scores of all labels of each word of the sentences, and the CRF layer finally obtains the probability of a label sequence by using the output of the BiLSTM layer; the named entity identification can divide mass aquatic data according to different named entities and divide the data of the same named entity together.
And extracting the relation, namely dividing the relation into a semantic relation and a syntactic relation. The relation extraction task adopts an Att-BiLSTM model, namely a relation extraction method of a bidirectional LSTM based on an attention mechanism. The model includes five parts: an input layer for inputting sentences into the model; an embedding layer mapping each word into a low-dimensional vector; LSTM layer: obtaining high-dimensional features from the embedded layer using Bi-LSTM; attention layer: generating a weight vector, and combining the feature time steps of each word by one sentence-level feature vector; and the output layer is used for carrying out relationship classification by using the sentence-level feature vectors. The relation extraction can identify sentence-level feature vectors, find out occurrence relation and rule among data according to the sentence feature vectors, and finish database division of corresponding aquatic data.
The event extraction adopts a dynamic multi-pooling convolutional neural network model, and the event extraction task is defined as a multi-classification task comprising two stages. The first stage is the classification of trigger words, each word in a sentence is identified by using a DMCNN model, whether the word is a trigger word is judged, and if the trigger word is contained in one sentence, namely the required named entities are consistent, the second stage is started to be executed; the second stage is argument classification, in which a similar DMCNN model is used to distinguish all entity arguments except trigger words in sentence words, and identify the arguments related to the trigger words and the argument roles played by the arguments, i.e. identify the events and cases related to named entities.
And S4.3, updating the classification knowledge base based on the classification data to obtain a final aquaculture knowledge base.
Specifically, the knowledge updating step includes knowledge reasoning, knowledge fusion and knowledge completion.
And (3) knowledge reasoning, namely mapping entities and relations in the knowledge graph to low-dimensional space vectors, and directly calculating the similarity between the entities by using mathematical expressions. The similarity relation between the aquaculture knowledge data which are subsequently supplemented and the entities of the existing data in the database can be established through knowledge reasoning, so that the classification of the aquaculture knowledge data which are subsequently supplemented is rapidly completed.
Knowledge fusion, which adopts a joint model to perform entity disambiguation, wherein the model is divided into three parts: the entity and word are embedded into a common vector space, focusing attention on word selection that provides information for disambiguation decisions, with parameterized conditional random field joint resolution. Through knowledge fusion, words with ambiguous decision information can be eliminated, and entity disambiguation and entity linking are solved.
Knowledge complementation is used for predicting the missing part of the triples in the knowledge graph, a dynamic knowledge graph complementation method is used, the embodiment preferably adopts a graph neural network model, the model is divided into a propagation model and an output model, the propagation model propagates information among nodes in the graph, and the output model uses a TransE model. The method can predict the lost entity type and the relation between the entities by utilizing the existing information, and can summarize and summarize the records and the related experiences in the prior aquaculture technical work, so that the implicit knowledge and the explicit knowledge are expressed in a unified form.
The data of the aquaculture knowledge base can be updated and supplemented in real time through knowledge reasoning, knowledge fusion and knowledge supplementation, and finally the aquaculture knowledge base can always record the aquaculture knowledge with the most timeliness and accuracy.
S5, constructing an intelligent decision model according to the aquaculture knowledge base and performing parameter optimization to obtain the aquaculture intelligent decision model;
s5.1, dividing the incidence relation between the multi-source data of the growth environment in the aquaculture knowledge base and the decision result to obtain knowledge nodes and inference nodes;
s5.2, constructing an intelligent decision model based on knowledge nodes and initializing to obtain initialization parameters;
specifically, the knowledge nodes comprise the association relation between the growth environment multi-source data and the decision result, the intelligent decision model which is input into the growth environment multi-source data and output into the decision result is constructed according to the association relation between the growth environment multi-source data and the decision result; the growth environment multisource data comprise data components such as an aquaculture pond change detection diagram, temperature, conductivity, PH, dissolved oxygen, ORP, ammonia nitrogen and underwater images of a target water area, and the connection parameters and weight ratio of each data component and a decision result are set. And inputting the growth environment multisource data and the decision result data stored in the knowledge nodes into the intelligent decision model for initialization to obtain initialization parameters of the intelligent decision model.
S5.3, performing attribute similarity matching on the inferred node and the knowledge node to obtain correct mapping from the inferred node to the knowledge node;
specifically, considering the requirements of the attribute of the inference node and the knowledge node, setting corresponding weights for the inference node and the knowledge node, and calculating the similarity function of the node attribute as follows:
wherein Sim (X i ,Y j ) Is node X i And Y j Attribute similarity, w p The weight of the p-th attribute of the node,to express concept x i And y j Similarity of the p-th attribute of (c).
And when the node attribute similarity exceeds a preset similarity threshold, the correct mapping from the inference node to the knowledge node is realized.
And S5.4, optimizing parameters of the intelligent decision model based on the correct mapping to obtain the aquaculture intelligent decision model.
Specifically, the weight of the node attribute and the preset similarity threshold are parameters to be adjusted, similar to model training, the node optimization is repeated for a plurality of times, and the parameters of the decision model are optimized according to the specific mapping result, so that the simulation effect of the decision model is optimal. According to specific aquaculture demands, the aquaculture intelligent decision model is subdivided into intelligent decision models in different decision directions, including an intelligent oxygenation model, an intelligent water changing model and an intelligent bait casting model.
S6, inputting the real-time environment multi-source data into an aquaculture intelligent decision model to obtain a production decision and uploading the production decision to a alliance block chain;
specifically, taking an intelligent oxygenation model as an example, the input growth environment multisource data has a plurality of attributes, including the types of fish fries, the cultivation time, the scale of a fishing farm and the coordinates of the cultivation farm, the temperature, the illumination, the oxygen content, the ammonia nitrogen concentration, the PH value and the carbon dioxide concentration. And inputting the data nodes into an intelligent oxygenation model, and outputting corresponding production decisions including whether to start the aerator and the opening time of the aerator by the model.
As shown in fig. 2, an intelligent decision-making aquaculture traceability system based on a blockchain includes:
the aquatic product data whole-flow acquisition module is used for acquiring multi-source data of a growth environment and production link data;
the production intelligent decision-making module is used for carrying out decision-making inference by combining the knowledge graph according to the aquatic product knowledge and the growth environment multisource data and the production link data provided by the aquatic product data whole-flow acquisition module so as to obtain a production decision;
the alliance blockchain network module is used for tracing the aquaculture production process through cloud service and blockchain technology;
the aquatic product data whole-flow collection module is connected with the alliance blockchain network module and is used for uploading the collected growth environment multi-source data and the production link data to the alliance blockchain network module;
the aquatic product data whole-flow acquisition module is connected with the production intelligent decision module and is used for providing acquired growth environment multi-source data and production link data;
the production intelligent decision module is connected with the alliance block chain network module and is used for uploading production decisions to the alliance block chain network module.
Furthermore, the data acquisition mode is that the 'space-world' integrated high-precision multidimensional three-dimensional monitoring is carried out on the aquaculture growth process through a remote sensing network, an Internet of things and an Internet three-network integration technology, namely comprehensive acquisition of aquatic data is carried out by comprehensively using space-based equipment, space-based equipment and foundation equipment, wherein the space-based equipment comprises high-resolution satellites and multi-source satellites, the space-based equipment comprises unmanned aerial vehicle aerial survey and airborne laser radar, and the foundation equipment comprises fixed sensors and portable acquisition equipment.
Further, the multi-source data of the growth environment are multi-source heterogeneous data of the growth environment of the aquatic products, which are acquired by using various acquisition equipment, and comprise an aquaculture pond change detection chart, the temperature, the conductivity, the PH, the dissolved oxygen, the ORP and the ammonia nitrogen of a target water area and an underwater image.
Further, collection equipment includes high-resolution remote sensing satellite, unmanned aerial vehicle, ground sensor, multi-angle camera, and according to aquaculture local pond and concrete topography, deployment high-resolution remote sensing satellite, unmanned aerial vehicle, ground sensor, multi-angle camera carry out data acquisition, and ground sensor includes water quality sensor, weather class sensor, utilizes above-mentioned equipment to acquire the real-time data of growing environment.
Further, the production link data is data of the whole flow of aquatic product production, including data of a seedling raising stage, a feeding and growing stage, a processing and packaging stage, a logistics stage and a sales stage, wherein:
recording breeding information of the fries in the fries growing stage, wherein the breeding information comprises fry source evidence and detection analysis reports;
the data of the feeding and growing stage mainly comprise environmental accurate monitoring, seed selection quality recording, feed application recording and growth harvest recording;
the processing and packaging stage data are recorded mainly by multi-angle cameras on the real-time information of the environment and the operation of operators;
the logistics stage data comprise accurate departure date, arrival date, a real-time transportation route map and real-time monitoring of temperature change in a transportation compartment through a camera;
the sales phase data mainly includes selling price, quality of the sold product, out-of-stock rate and out-of-stock period.
Further, the production intelligent decision module comprises an aquaculture knowledge base unit and an intelligent decision unit, wherein:
the aquaculture knowledge base unit comprises an aquaculture base database, an aquaculture resource database, aquaculture dynamic knowledge, aquaculture knowledge interaction information and an aquaculture related case base; the construction steps of the aquaculture knowledge base unit are information extraction and knowledge updating. The information extraction comprises named entity identification, relation extraction and event extraction; the knowledge updating comprises knowledge reasoning, knowledge fusion and knowledge completion; carrying out big data analysis and processing and knowledge extraction and fusion on aquaculture scene data through information extraction and knowledge updating to obtain knowledge after aquaculture product organization encapsulation;
the intelligent decision unit is used for carrying out decision inference according to the comprehensive data provided by the aquaculture knowledge base unit and the growth environment multi-source data provided by the aquatic product data whole-flow acquisition module to obtain decision information;
the specific decision process of the real-time monitoring of the water quality of the specific embodiment of the system comprises the steps of counting and analyzing the aquiculture data of the past year through an algorithm on the basis of acquiring real and reliable abnormal data of the water quality of the aquaculture in Guangdong province by an aquaculture knowledge base unit, and when the numerical value (dissolved oxygen, conductivity and the like) of certain water quality detection parameters of the actual aquiculture environment changes and exceeds a normal range, possibly representing the occurrence of water deterioration, providing timely and accurate early warning information of the abnormal water quality for aquaculture producers in time by the system, carrying out intelligent decision, and storing decision records in a alliance block chain network module.
Further, the federated blockchain network module includes an object identification layer, a data acquisition layer, a data processing layer, and a data service layer, wherein:
the object identification layer is used for generating and managing traceability codes and coded data carriers of aquatic products and all circulation links thereof, and the traceability code formats are uniform and unique; the traceability code is created according to an application identifier AI provided by the GS1 standard, and comprises an aquatic product manufacturer code, a production place code, an aquatic product project code, a product batch code, a code in different package forms, other production raw material codes and an aquatic product circulation code.
The data acquisition layer analyzes and screens the original data acquired by various devices, calculates and converts the original data into effective information, and stores the effective information in a back-end database.
The data processing layer is used for processing the acquired data and storing the acquired data in a block chain network, the data storage adopts a multi-chain mode, and the data of different links is stored by using a single block chain network. Building a alliance blockchain network represented by fishermen, processors, logistics providers and sellers. A ranking service is created and authentication nodes are deployed for each role node. When data is transmitted, the node initiates a uplink transaction, decides which node to process the transaction through the ordering service, decides which node obtains the accounting right by using the consensus mechanism, records the transaction, and each node automatically backs up the account book. Each link from production to circulation of the aquatic product needs to inherit the traceability information of the previous link (the step is not needed by the data original node), the traceability information of the current link is generated, the relevant connection information is added and then uploaded to the blockchain, and meanwhile the traceability information of the current link is transmitted to the next link through the physical label for use by the subsequent link.
The data service layer is used for processing a query request of a consumer end and checking whether the full-chain data is tampered or not to obtain full-chain traceability information of the corresponding aquatic products. The consumer initiates a tracing inquiry request through a tracing code on the aquatic product package, after the data service layer receives the request, inquiry and verification of user identity information, the product information is bound to the user account, whether the blocks on the main chain are matched or not is checked through a hash algorithm, whether data are tampered or not is known, and tracing information of corresponding products is returned.
The content in the method embodiment is applicable to the system embodiment, the functions specifically realized by the system embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method embodiment.
While the preferred embodiment of the present application has been described in detail, the application is not limited to the embodiment, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.
Claims (9)
1. The intelligent decision aquaculture tracing method based on the blockchain is characterized by comprising the following steps of:
constructing an aquaculture traceability alliance blockchain according to the production flow of the aquatic products;
monitoring the aquatic product production links to obtain production link data and storing the production link data into a alliance block chain;
monitoring the aquatic product growth environment to obtain environment multi-source data and periodically uploading the environment multi-source data to a alliance blockchain;
constructing an intelligent decision model according to the aquaculture knowledge base and performing parameter optimization to obtain the aquaculture intelligent decision model;
and inputting the real-time environment multi-source data into an aquaculture intelligent decision model to obtain a production decision and uploading the production decision to the alliance blockchain.
2. The blockchain-based intelligent decision aquaculture traceability method according to claim 1, further comprising the steps of collecting aquaculture data and constructing an aquaculture knowledge base, and specifically comprising:
dividing an initial aquaculture knowledge base to obtain a classification knowledge base;
acquiring aquaculture data and classifying to obtain classified data;
updating the classification knowledge base based on the classification data to obtain a final aquaculture knowledge base.
3. The blockchain-based intelligent decision aquaculture traceability method according to claim 1, wherein the step of constructing the aquaculture traceability alliance blockchain according to the production flow of the aquaculture comprises the following steps:
dividing and deploying alliance blockchain members according to the aquatic product production flow to obtain an alliance blockchain network;
coding according to a preset standard coding format based on each circulation link of the aquatic product to obtain a alliance block chain traceability code;
and formulating relevant configuration files based on a consistent scheme of alliance members, and combining an alliance blockchain network and alliance blockchain traceability codes to obtain the aquaculture traceable alliance blockchain.
4. The blockchain-based intelligent decision aquaculture traceability method according to claim 1, wherein the step of monitoring the production links of the aquatic products to obtain production link data and storing the production link data in the alliance blockchain specifically comprises the following steps:
dividing the production links of the aquatic products into stages to obtain a seedling raising stage, a feeding and growing stage, a processing and packaging stage, a logistics stage and a sales stage;
monitoring each production link of the aquatic product to obtain generation link data;
and storing the data of each production link into an independent blockchain network through a multi-chain data storage mode, and generating the traceability information of each link.
5. The blockchain-based intelligent decision aquaculture traceability method is characterized in that the monitoring mode of the aquatic product growth environment is space-world integrated high-precision multidimensional three-dimensional monitoring.
6. The blockchain-based intelligent decision aquaculture traceability method according to claim 1, wherein the steps of constructing an intelligent decision model according to an aquaculture knowledge base and performing parameter optimization to obtain the aquaculture intelligent decision model specifically comprise:
dividing the association relation between the growth environment multisource data and the decision result in the aquaculture knowledge base to obtain knowledge nodes and inference nodes;
constructing an intelligent decision model based on knowledge nodes and initializing to obtain initialization parameters;
performing attribute similarity matching on the inferred node and the knowledge node to obtain correct mapping from the inferred node to the knowledge node;
and optimizing parameters of the intelligent decision model based on the correct mapping to obtain the aquaculture intelligent decision model.
7. An intelligent decision-making aquaculture traceability system based on a blockchain is characterized by comprising:
the aquatic product data whole-flow acquisition module is used for acquiring multi-source data of a growth environment and production link data;
the production intelligent decision-making module is used for carrying out decision-making inference by combining the knowledge graph according to the aquatic product knowledge and the growth environment multisource data and the production link data provided by the aquatic product data whole-flow acquisition module so as to obtain a production decision;
the alliance blockchain network module is used for tracing the aquaculture production process through cloud service and blockchain technology;
the aquatic product data whole-flow collection module is connected with the alliance blockchain network module and is used for uploading the collected growth environment multi-source data and the production link data to the alliance blockchain network module;
the aquatic product data whole-flow acquisition module is connected with the production intelligent decision module and is used for providing acquired growth environment multi-source data and production link data;
the production intelligent decision module is connected with the alliance block chain network module and is used for uploading production decisions to the alliance block chain network module.
8. The blockchain-based intelligent decision aquaculture traceability system of claim 7, wherein the production intelligent decision module comprises an aquaculture knowledge base unit and an intelligent decision unit, wherein:
the aquatic product knowledge base unit is used for carrying out big data analysis and processing on aquatic product scene data and knowledge extraction and fusion to obtain knowledge of aquatic product tissues after encapsulation;
the intelligent decision unit is used for carrying out decision inference according to the comprehensive data provided by the aquatic product knowledge base unit and the growth environment multi-source data provided by the aquatic product data whole-flow acquisition module to obtain decision information.
9. The blockchain-based intelligent decision aquaculture traceability system of claim 7, wherein the federated blockchain network module includes an object identification layer, a data acquisition layer, a data processing layer, and a data service layer, wherein:
the object identification layer is used for generating and managing traceability codes and coded data carriers of aquatic products and various circulation links thereof;
the data acquisition layer is used for reading and analyzing the coded data carrier and uploading the data to the back-end database according to the address information in the data unit;
the data processing layer is used for processing the acquired data and storing the acquired data into a block chain network;
the data service layer is used for processing a query request of a consumer end and checking whether the full-chain data is tampered or not to obtain full-chain traceability information of the corresponding aquatic products.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310595213.2A CN116579576A (en) | 2023-05-25 | 2023-05-25 | Intelligent decision aquaculture tracing method and system based on blockchain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310595213.2A CN116579576A (en) | 2023-05-25 | 2023-05-25 | Intelligent decision aquaculture tracing method and system based on blockchain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116579576A true CN116579576A (en) | 2023-08-11 |
Family
ID=87539410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310595213.2A Pending CN116579576A (en) | 2023-05-25 | 2023-05-25 | Intelligent decision aquaculture tracing method and system based on blockchain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116579576A (en) |
-
2023
- 2023-05-25 CN CN202310595213.2A patent/CN116579576A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20150371161A1 (en) | System and methods for identifying, evaluating and predicting land use and agricultural production | |
| CN109146130A (en) | Agricultural product customization is planted and whole process is traced to the source platform and method | |
| CN104732328A (en) | Agricultural Internet of Things platform system | |
| Honey et al. | From rags to fishes: data-poor methods for fishery managers | |
| US20210256631A1 (en) | System And Method For Digital Crop Lifecycle Modeling | |
| Naud et al. | Support to decision-making | |
| Corti et al. | Evaluation of in-season management zones from high-resolution soil and plant sensors | |
| Jahan et al. | Machine learning for global food security: a concise overview | |
| US20220309595A1 (en) | System and Method for Managing and Operating an Agricultural-Origin-Product Manufacturing Supply Chain | |
| CN116579576A (en) | Intelligent decision aquaculture tracing method and system based on blockchain | |
| Gkikas et al. | Artificial Intelligence (AI) use for e-Governance in agriculture: Exploring the bioeconomy landscape | |
| Rabhi et al. | A connected farm metamodeling using advanced information technologies for an agriculture 4.0 | |
| Mundada | Optimized Farming: Crop Recommendation System Using Predictive Analytics. | |
| Bilbao-Arechabala et al. | A practical approach to cross-agri-domain interoperability and integration | |
| Akerkar et al. | Big data in aquaculture | |
| Arooj et al. | Modeling smart agriculture using SensorML | |
| Poblete-Echeverría et al. | Digital technologies: smart applications in viticulture | |
| Márta et al. | Information Technology Drivers in Smart Farming Management Systems | |
| Zeginis et al. | A semantic meta-model for data integration and exploitation in precision agriculture and livestock farming | |
| Zhang et al. | APT3: Automated product traceability trees generated from GPS tracks | |
| Patil et al. | 11 Role of Data-Centric Artificial Intelligence | |
| Swain et al. | Big data application in fisheries with special reference to inland fisheries sector in India | |
| Balaji et al. | Predictive Analysis in Smart Agriculture | |
| Casten Carlberg et al. | Artificial Intelligence in Agriculture: Opportunities and Challenges | |
| Wangome | A Rainfall prediction model using long short-term neural networks for improved crop productivity: a case of maize planting in Machakos County. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |